@BigWayne111@DefiyantlyFree The candidate who ran a positive campaign isn’t the cause of 15% turnout. But far be it from me to persuade you to chill out on your quest to call people retarded.
@BigWayne111@DefiyantlyFree Too bad Steve Hilton’s campaign and supporters didn’t put more effort into leading those 85% to want to vote, instead of henpecking a fraction of voters who wanted a different Republican to be the governor.
@ChadBianco Crazy how the histrionic comments act as though Steve Hilton has a better chance of winning the general election than Chad Bianco. Seemingly unaware that many Democrat candidates are in the primary race (“splitting the vote” of Democrats too).
Disappointed that @OpenAI took away the gpt-5.3-codex model from ChatGPT subscription users. Users are left with models that hit usage limits way faster. The Codex Models documentation page doesn't even reflect this model as unavailable.
To simplify our Codex compute fleet management, we will be sunsetting GPT-5.2 and GPT-5.3-Codex in Codex on June 2nd when logged in with your ChatGPT account.
For free plans, GPT-5.5 will be the default frontier model to build and work with going forward.
These models will remain available on our API.
Gpt 5.3 codex is no more available through your chatgpt subscription
Rip to the greatest model
The model that made me and many others go bullish on codex
“Asked” is an understatement - a mob of Jews terrorized the Roman governor to execute Jesus.
John 19:6-8
[6] When the chief priests and the officers saw him, they cried out, “Crucify him, crucify him!” Pilate said to them, “Take him yourselves and crucify him, for I find no guilt in him.” [7] The Jews answered him, “We have a law, and according to that law he ought to die because he has made himself the Son of God.” [8] When Pilate heard this statement, he was even more afraid.
@StepFun_ai@NousResearch I’m not completely opposed to using a service that mines user data but it’s important to understand how. I’d consider creating an agent profile assigned to such a model and only ask the agent to do things involving open source data that I don’t care to keep private.
@StepFun_ai@NousResearch Often there is a catch to free services. Do you use user data, i.e. for training, etc?
OpenRouter offers free models but I used the global config option to disabled routing to any provider who leverages their user data for training.
I guess it comes down to what counts as “prove”. If someone claimed something absurd, e.g. that you rode an invisible flying unicorn to an island, could you “actually prove that you did no such thing” - in the strict sense of the word “prove”? Granted it’s probable you didn’t, and they have no evidence - but “absence of evidence isn’t evidence of absence”. It’s hard enough to come up with evidence that the person didn’t believe their own damaging lie.
@NousResearch@browserbase@grok How vulnerable is Hermes Agent to prompt injection by malicious websites that get visited by the agent when trying to research information?
@BrianRoemmele@AlexAdams1776 Nothing about this is "iPhone mode" and stop motion is a video technique that's over a century old. Old films that lack grainy artifacts could have been digitally restored rather than created from scratch by AI.
Hermes Agent tip of the day:
There are 4 ways to deal with the model while its running,
- Message it, by default, it will interrupt the agent loop, stopping it and making it respond to your new message
- /queue will queue up a message that will fire after the agent loop completes
- /bg or /btw will run a parallel prompt that is async
And
- /steer will inject a guidance message into the next tool calls result sent to the model during an agent loop, to try to guide the rest of its trajectory